INCIDENT MAP

Browse / Model Evasion / AML.CS0003

Bypassing Cylance's AI Malware Detection

AML.CS0003 · 2019-09-07 case study

Class
Model Evasion
Technique
Craft Adversarial Data: Manual Modification
Target
CylancePROTECT, Cylance Smart Antivirus (Exercise)

How it worked

  1. Reconnaissance · Search Open Technical Databases

    The researchers read publicly available information about Cylance's AI Malware detector. They gathered this information from various sources such as public talks as well as patent submissions by Cylance.

  2. AI Model Access · AI-Enabled Product or Service

    The researchers had access to Cylance's AI-enabled malware detection software.

  3. Discovery · Discover AI Model Outputs

    The researchers enabled verbose logging, which exposes the inner workings of the ML model, specifically around reputation scoring and model ensembling.

  4. Resource Development · Develop Capabilities: Adversarial AI Attacks

    The researchers used the reputation scoring information to reverse engineer which attributes provided what level of positive or negative reputation.
    Along the way, they discovered a secondary model which was an override for the first model.
    Positive assessments from the second model overrode the decision of the core ML model.

  5. AI Attack Adaptation · Craft Adversarial Data: Manual Modification

    Using this knowledge, the researchers fused attributes of known good files with malware to manually create adversarial malware.

  6. Defense Evasion · Evade AI Model

    Due to the secondary model overriding the primary, the researchers were effectively able to bypass the ML model.

Summary

Researchers at Skylight were able to create a universal bypass string that evades detection by Cylance's AI Malware detector when appended to a malicious file.

References

Source: MITRE ATLAS case studies, used under Apache 2.0.